SUBTOPIC-BASED MULTI-DOCUMENT SUMMARIZATION

摘要：

This paper proposes a novel approach for multi-document summarization based on subtopic segmentation. It firstly detects the subtopics in a topic, and then finds the central sentence for each subtopic. The sentences are scored based on their importance in the document and in the subtopic. Two anti-redundancy strategies are used to extract sentences to form summarization. Since our approach is intrinsically incremental, it is effective when new documents are added to the document set. Experimental results indicate that the proposed approach is effective and efficient.

关键词： Multi-document summarization Topic segmentation Topic Detection and Tracking Anti-redundancy strategy

作者: LIN DAI JI-LIANG TANG YUN-QING XIA

作者单位: Beijing Laboratory of Intelligent Information Technology, School of Computer Science, Beijing Instit Tsinghua National Lab for Information Science and Technology, Tsinghua University, Beijing 100084, C

会议类型: 国际会议

会议名称: 2009 International Conference on Machine Learning and Cybernetics(2009机器学习与控制论国际会议)

会议地点: 保定

会议语种:英文

页码: 3505-3510

在线出版日期: 2009-07-12（万方平台首次上网日期，不代表论文的发表时间）